Upload Date | November 19 2024 07:20 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B2083) |
Model | Mac16,5 |
Model ID | Mac16,5 |
Motherboard | Mac16,5 |
CPU Information | |
---|---|
Name | Apple M4 Max |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Max |
Base Frequency | 4.51 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
9081
1.69 KIPS |
|
Image Classification (HP)
|
100% |
9490
1.76 KIPS |
|
Image Classification (Q)
|
97% |
8331
1.55 KIPS |
|
Image Segmentation (SP)
|
100% |
16461
266.8 IPS |
|
Image Segmentation (HP)
|
100% |
17650
286.1 IPS |
|
Image Segmentation (Q)
|
99% |
18603
301.6 IPS |
|
Pose Estimation (SP)
|
100% |
80333
93.7 IPS |
|
Pose Estimation (HP)
|
100% |
83719
97.7 IPS |
|
Pose Estimation (Q)
|
95% |
78966
92.6 IPS |
|
Object Detection (SP)
|
100% |
8653
686.3 IPS |
|
Object Detection (HP)
|
100% |
9431
748.1 IPS |
|
Object Detection (Q)
|
91% |
7997
639.0 IPS |
|
Face Detection (SP)
|
100% |
35281
419.2 IPS |
|
Face Detection (HP)
|
100% |
36940
438.9 IPS |
|
Face Detection (Q)
|
100% |
27582
327.7 IPS |
|
Depth Estimation (SP)
|
100% |
42579
328.0 IPS |
|
Depth Estimation (HP)
|
99% |
43869
338.0 IPS |
|
Depth Estimation (Q)
|
85% |
36325
283.9 IPS |
|
Style Transfer (SP)
|
100% |
186263
239.4 IPS |
|
Style Transfer (HP)
|
100% |
202239
260.0 IPS |
|
Style Transfer (Q)
|
96% |
188302
243.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
26119
964.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
27092
1.00 KIPS |
|
Image Super-Resolution (Q)
|
99% |
21651
799.5 IPS |
|
Text Classification (SP)
|
100% |
2954
3.94 KIPS |
|
Text Classification (HP)
|
100% |
5419
7.23 KIPS |
|
Text Classification (Q)
|
93% |
5290
7.10 KIPS |
|
Machine Translation (SP)
|
100% |
3246
55.9 IPS |
|
Machine Translation (HP)
|
100% |
3311
57.0 IPS |
|
Machine Translation (Q)
|
98% |
1854
32.0 IPS |